© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3097
    Prev
    Next
    INDEX
    Explanations

    molar ratios and their related quantities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.72
    ########.
    -0.55
    GOTREF
    -0.55
    enko
    -0.55
    igraph
    -0.52
    lielmo
    -0.52
    AndEndTag
    -0.52
    गत
    -0.51
    Millisecond
    -0.51
    oursquare
    -0.51
    POSITIVE LOGITS
     ratio
    2.53
     Ratio
    2.23
     ratios
    2.21
    ratio
    2.19
    Ratio
    2.04
     RATIO
    2.02
     Ratios
    1.97
    ratios
    1.85
    RATIO
    1.75
     proportion
    1.40
    Activations Density 0.538%

    No Known Activations